Skip to main content Accessibility help
×
Home

A Generalizable, Data-Driven Approach to Predict Daily Risk of Clostridium difficile Infection at Two Large Academic Health Centers

  • Jeeheh Oh (a1), Maggie Makar (a2), Christopher Fusco (a3), Robert McCaffrey (a3), Krishna Rao (a4), Erin E. Ryan (a5) (a6), Laraine Washer (a4) (a7), Lauren R. West (a5) (a6), Vincent B. Young (a4) (a8), John Guttag (a2), David C. Hooper (a5) (a6) (a9), Erica S. Shenoy (a5) (a6) (a9) (a10) and Jenna Wiens (a1)...

Abstract

OBJECTIVE

An estimated 293,300 healthcare-associated cases of Clostridium difficile infection (CDI) occur annually in the United States. To date, research has focused on developing risk prediction models for CDI that work well across institutions. However, this one-size-fits-all approach ignores important hospital-specific factors. We focus on a generalizable method for building facility-specific models. We demonstrate the applicability of the approach using electronic health records (EHR) from the University of Michigan Hospitals (UM) and the Massachusetts General Hospital (MGH).

METHODS

We utilized EHR data from 191,014 adult admissions to UM and 65,718 adult admissions to MGH. We extracted patient demographics, admission details, patient history, and daily hospitalization details, resulting in 4,836 features from patients at UM and 1,837 from patients at MGH. We used L2 regularized logistic regression to learn the models, and we measured the discriminative performance of the models on held-out data from each hospital.

RESULTS

Using the UM and MGH test data, the models achieved area under the receiver operating characteristic curve (AUROC) values of 0.82 (95% confidence interval [CI], 0.80–0.84) and 0.75 ( 95% CI, 0.73–0.78), respectively. Some predictive factors were shared between the 2 models, but many of the top predictive factors differed between facilities.

CONCLUSION

A data-driven approach to building models for estimating daily patient risk for CDI was used to build institution-specific models at 2 large hospitals with different patient populations and EHR systems. In contrast to traditional approaches that focus on developing models that apply across hospitals, our generalizable approach yields risk-stratification models tailored to an institution. These hospital-specific models allow for earlier and more accurate identification of high-risk patients and better targeting of infection prevention strategies.

Infect Control Hosp Epidemiol 2018;39:425–433

  • View HTML
    • Send article to Kindle

      To send this article to your Kindle, first ensure no-reply@cambridge.org is added to your Approved Personal Document E-mail List under your Personal Document Settings on the Manage Your Content and Devices page of your Amazon account. Then enter the ‘name’ part of your Kindle email address below. Find out more about sending to your Kindle. Find out more about sending to your Kindle.

      Note you can select to send to either the @free.kindle.com or @kindle.com variations. ‘@free.kindle.com’ emails are free but can only be sent to your device when it is connected to wi-fi. ‘@kindle.com’ emails can be delivered even when you are not connected to wi-fi, but note that service fees apply.

      Find out more about the Kindle Personal Document Service.

      A Generalizable, Data-Driven Approach to Predict Daily Risk of Clostridium difficile Infection at Two Large Academic Health Centers
      Available formats
      ×

      Send article to Dropbox

      To send this article to your Dropbox account, please select one or more formats and confirm that you agree to abide by our usage policies. If this is the first time you use this feature, you will be asked to authorise Cambridge Core to connect with your <service> account. Find out more about sending content to Dropbox.

      A Generalizable, Data-Driven Approach to Predict Daily Risk of Clostridium difficile Infection at Two Large Academic Health Centers
      Available formats
      ×

      Send article to Google Drive

      To send this article to your Google Drive account, please select one or more formats and confirm that you agree to abide by our usage policies. If this is the first time you use this feature, you will be asked to authorise Cambridge Core to connect with your <service> account. Find out more about sending content to Google Drive.

      A Generalizable, Data-Driven Approach to Predict Daily Risk of Clostridium difficile Infection at Two Large Academic Health Centers
      Available formats
      ×

Copyright

Corresponding author

Address correspondence to Jenna Wiens, PhD, 2260 Hayward Street, Ann Arbor, MI 48109 (wiensj@umich.edu) or Erica S. Shenoy, MD, PhD, 55 Fruit Street, Bulfinch 334, Boston, MA (eshenoy@partners.org).

Footnotes

Hide All
a

First authors of equal contribution.

b

Senior authors of equal contribution.

Footnotes

References

Hide All
1. Lessa, FC, Winston, LG, McDonald, LC. Burden of Clostridium difficile infection in the United States. N Engl J Med 2015;372:23692370.
2. Barbut, F, Surgers, L, Eckert, C, et al. Does a rapid diagnosis of Clostridium difficile infection impact on quality of patient management? Clin Microbiol Infect 2014;20:136144.
3. Cohen, SH, Gerding, DN, Johnson, S, et al. Clinical practice guidelines for Clostridium difficile infection in adults: 2010 update by the society for healthcare epidemiology of America (SHEA) and the infectious diseases society of America (IDSA). Infect Control Hosp Epidemiol 2010;31:431455.
4. Dubberke, ER, Carling, P, Carrico, R, et al. Strategies to prevent Clostridium difficile infections in acute care hospitals: 2014 update. Infect Control Hosp Epidemiol 2014;35:628645.
5. Na, X, Martin, AJ, Sethi, S, et al. A multi-center prospective derivation and validation of a clinical prediction tool for severe Clostridium difficile infection. PLoS One 2015;10:e0123405.
6. Press, A, Ku, B, McCullagh, L, Rosen, L, Richardson, S, McGinn, T. Developing a clinical prediction rule for first hospital-onset Clostridium difficile infections: a retrospective observational study. Infect Control Hosp Epidemiol 2016;37:896900.
7. Chandra, S, Thapa, R, Marur, S, Jani, N. Validation of a clinical prediction scale for hospital-onset Clostridium difficile infection. J Clin Gastroenterol 2014;48:419422.
8. Zilberberg, MD, Reske, K, Olsen, M, Yan, Y, Dubberke, ER. Risk factors for recurrent Clostridium difficile infection (CDI) hospitalization among hospitalized patients with an initial CDI episode: a retrospective cohort study. BMC Infect Dis 2014;14:306.
9. Chalmers, JD, Akram, AR, Singanayagam, A, Wilcox, MH, Hill, AT. Risk factors for Clostridium difficile infection in hospitalized patients with community-acquired pneumonia. J Infect 2016;73:4553.
10. Henrich, TJ, Krakower, D, Bitton, A, Yokoe, DS. Clinical risk factors for severe Clostridium difficile–associated disease. Emerg Infect Dis 2009;15:415422.
11. Wiens, J, Campbell, WN, Franklin, ES, Guttag, JV, Horvitz, E. Learning data-driven patient risk stratification models for Clostridium difficile . Open Forum Infect Dis 2014;1:ofu045.
12. Miller, AC, Polgreen, LA, Cavanaugh, JE, Polgreen, PM. Hospital Clostridium difficile infection (CDI) incidence as a risk factor for hospital-associated CDI. Am J Infect Control 2016;44:825829.
13. DiDiodato, G, McArthur, L. Evaluating the effectiveness of an antimicrobial stewardship program on reducing the incidence rate of healthcare-associated Clostridium difficile infection: a non-randomized, stepped wedge, single-site, observational study. PLoS One 2016;11:e0157671.
14. Wiens, J, Guttag, J, Horvitz, E. A study in transfer learning: leveraging data from multiple hospitals to enhance hospital-specific predictions. J Am Med Inform Assoc 2014;21:699706.
15. Identifying healthcare-associated infections (HAI) for NHSN surveillance. Centers for Disease Control and Prevention website. https://www.cdc.gov/nhsn/pdfs/pscmanual/2psc_identifyinghais_nhsncurrent.pdf. Published 2017. Accessed Janaury 22, 2018.
16. McDonald, LC, Coignard, B, Dubberke, E, Song, X, Horan, T, Kutty, PK. Ad Hoc Clostridium difficile Surveillance Working Group. Recommendations for surveillance of Clostridium difficile-associated disease. Infect Control Hosp Epidemiol 2007;28:140145.
17. Dubberke, ER, Reske, KA, Olsen, MA, et al. Evaluation of Clostridium difficile–associated disease pressure as a risk factor for C difficile–associated disease. Arch Intern Med 2007;167:10921097.
18. Wiens, J, Guttag, J, Horvitz, E. Patient risk stratification with time-varying parameters: a multitask learning approach. J Mach Learn Res 2016;17:27972819.
19. Ma, GK, Pegues, DA, Kochman, ML, et al. Implementation of a systematic culturing program to monitor the efficacy of endoscope reprocessing: outcomes and costs. Gastrointest Endosc 2018;87:104109.
20. Vardakas, KZ, Trigkidis, KK, Boukouvala, E, Falagas, ME. Clostridium difficile infection following systemic antibiotic administration in randomised controlled trials: a systematic review and meta-analysis. Int J Antimicrob Agents 2016;48:110.
21. Tariq, R, Singh, S, Gupta, A, Pardi, DS, Khanna, S. Association of gastric acid suppression with recurrent Clostridium difficile infection: a systematic review and meta-analysis. JAMA Intern Med 2017;177:784791.
22. Longtin, Y, Paquet-Bolduc, B, Gilca, R, et al. Effect of detecting and isolating Clostridium difficile carriers at hospital admission on the incidence of C difficile infections: a quasi-experimental controlled study. JAMA Intern Med 2016;176:796804.
23. Shen, NT, Maw, A, Tmanova, LL, et al. Timely use of probiotics in hospitalized adults prevents Clostridium difficile infection: a systematic review with meta-regression analysis. Gastroenterology 2017;152:18891900.e9.
24. Kokai-Kun, JF, Roberts, T, Coughlin, O, et al. The oral beta-lactamase SYN-004 (ribaxamase) degrades ceftriaxone excreted into the intestine in phase 2a clinical studies. Antimicrob Agents Chemother 2017;61:e0219716.
25. Manian, FA, Griesnauer, S, Bryant, A. Implementation of hospital-wide enhanced terminal cleaning of targeted patient rooms and its impact on endemic Clostridium difficile infection rates. Am J Infect Control 2013;41:537541.
26. Anderson, DJ, Gergen, MF, Smathers, E, et al. Decontamination of targeted pathogens from patient rooms using an automated ultraviolet-C-emitting Device. Infect Control Hosp Epidemiol 2013;34:466471.
27. Han, JH, Sullivan, N, Leas, BF, et al. Cleaning hospital room surfaces to prevent health care–associated infections: a technical brief. Ann Intern Med 2015;163:598607.
28. Mills, JP, Rao, K, Young, VB. Probiotics for prevention of Clostridium difficile infection. Curr Opin Gastroenterol 2018;34:310.
29. Gulshan, V, Peng, L, Coram, M, et al. Development and validation of a deep learning algorithm for detection of diabetic retinopathy in retinal fundus photographs. JAMA 2016;316:24022410.
30. Walters, SJ, dos Anjos Henriques-Cadby, IB, Bortolami, O, et al. Recruitment and retention of participants in randomised controlled trials: a review of trials funded and published by the United Kingdom Health Technology Assessment Programme. BMJ Open 2017;7:e015276.
31. Wong, H-H, et al. Examination of clinical trial costs and barriers for drug development final. Office of the Assistant Secretary for Planning and Evaluation. US Department of Health & Human Services website. https://aspe.hhs.gov/report/examination-clinical-trial-costs-and-barriers-drug-development. Published 2014. Accessed January 22, 2018.
Type Description Title
WORD
Supplementary materials

Oh et al. supplementary material
Table S1

 Word (19 KB)
19 KB

A Generalizable, Data-Driven Approach to Predict Daily Risk of Clostridium difficile Infection at Two Large Academic Health Centers

  • Jeeheh Oh (a1), Maggie Makar (a2), Christopher Fusco (a3), Robert McCaffrey (a3), Krishna Rao (a4), Erin E. Ryan (a5) (a6), Laraine Washer (a4) (a7), Lauren R. West (a5) (a6), Vincent B. Young (a4) (a8), John Guttag (a2), David C. Hooper (a5) (a6) (a9), Erica S. Shenoy (a5) (a6) (a9) (a10) and Jenna Wiens (a1)...

Metrics

Altmetric attention score

Full text views

Total number of HTML views: 0
Total number of PDF views: 0 *
Loading metrics...

Abstract views

Total abstract views: 0 *
Loading metrics...

* Views captured on Cambridge Core between <date>. This data will be updated every 24 hours.

Usage data cannot currently be displayed